GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Jingqiu, Fan, Lue, Chen, Xuesong, Huang, Linjiang, Liu, Si, Li, Hongsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913623568285696
author Zhou, Jingqiu
Fan, Lue
Chen, Xuesong
Huang, Linjiang
Liu, Si
Li, Hongsheng
author_facet Zhou, Jingqiu
Fan, Lue
Chen, Xuesong
Huang, Linjiang
Liu, Si
Li, Hongsheng
contents In this paper, we present GaussianPainter, the first method to paint a point cloud into 3D Gaussians given a reference image. GaussianPainter introduces an innovative feed-forward approach to overcome the limitations of time-consuming test-time optimization in 3D Gaussian splatting. Our method addresses a critical challenge in the field: the non-uniqueness problem inherent in the large parameter space of 3D Gaussian splatting. This space, encompassing rotation, anisotropic scales, and spherical harmonic coefficients, introduces the challenge of rendering similar images from substantially different Gaussian fields. As a result, feed-forward networks face instability when attempting to directly predict high-quality Gaussian fields, struggling to converge on consistent parameters for a given output. To address this issue, we propose to estimate a surface normal for each point to determine its Gaussian rotation. This strategy enables the network to effectively predict the remaining Gaussian parameters in the constrained space. We further enhance our approach with an appearance injection module, incorporating reference image appearance into Gaussian fields via a multiscale triplane representation. Our method successfully balances efficiency and fidelity in 3D Gaussian generation, achieving high-quality, diverse, and robust 3D content creation from point clouds in a single forward pass.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance
Zhou, Jingqiu
Fan, Lue
Chen, Xuesong
Huang, Linjiang
Liu, Si
Li, Hongsheng
Computer Vision and Pattern Recognition
In this paper, we present GaussianPainter, the first method to paint a point cloud into 3D Gaussians given a reference image. GaussianPainter introduces an innovative feed-forward approach to overcome the limitations of time-consuming test-time optimization in 3D Gaussian splatting. Our method addresses a critical challenge in the field: the non-uniqueness problem inherent in the large parameter space of 3D Gaussian splatting. This space, encompassing rotation, anisotropic scales, and spherical harmonic coefficients, introduces the challenge of rendering similar images from substantially different Gaussian fields. As a result, feed-forward networks face instability when attempting to directly predict high-quality Gaussian fields, struggling to converge on consistent parameters for a given output. To address this issue, we propose to estimate a surface normal for each point to determine its Gaussian rotation. This strategy enables the network to effectively predict the remaining Gaussian parameters in the constrained space. We further enhance our approach with an appearance injection module, incorporating reference image appearance into Gaussian fields via a multiscale triplane representation. Our method successfully balances efficiency and fidelity in 3D Gaussian generation, achieving high-quality, diverse, and robust 3D content creation from point clouds in a single forward pass.
title GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.17715